© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20538
    Prev
    Next
    INDEX
    Explanations

    my/your keep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĭ¢
    -0.06
    ament
    -0.06
    -looking
    -0.06
    å¤ļ彩çļĦ
    -0.06
    ment
    -0.05
    orsk
    -0.05
    年以ä¸ĭ
    -0.05
    管æīĢ
    -0.05
    wy
    -0.05
    oga
    -0.05
    POSITIVE LOGITS
    strap
    0.07
    steen
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.06
    adecimal
    0.06
    èĮĥåĽ´å¹¿
    0.06
    人æĹł
    0.06
    tecnolog
    0.06
    åŃIJåĴĮ
    0.06
    epis
    0.06
    efficient
    0.06
    Activations Density 0.014%

    No Known Activations